drm/xe/lrc: Allow to add user commands on context switch

During validation it's useful to allows additional commands to be
executed on context switch. Fetch the commands from configfs (to be
added) and add them to the WA BB.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250916-wa-bb-cmds-v5-3-306bddbc15da@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>

Author: Lucas De Marchi

drivers/gpu/drm/xe/xe_configfs.c

@@ -633,6 +633,19 @@ bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev)
 	return ret;
 }
 
+/**
+ * xe_configfs_get_ctx_restore_post_bb - get configfs ctx_restore_post_bb setting
+ * @pdev: pci device
+ *
+ * Return: post_ctx_restore setting in configfs
+ */
+u32 xe_configfs_get_ctx_restore_post_bb(struct pci_dev *pdev,
+					enum xe_engine_class class,
+					const u32 **cs)
+{
+	return 0;
+}
+
 int __init xe_configfs_init(void)
 {
 	int ret;

drivers/gpu/drm/xe/xe_configfs.h

@@ -8,6 +8,8 @@
 #include <linux/limits.h>
 #include <linux/types.h>
 
+#include <xe_hw_engine_types.h>
+
 struct pci_dev;
 
 #if IS_ENABLED(CONFIG_CONFIGFS_FS)
@@ -17,13 +19,17 @@ void xe_configfs_check_device(struct pci_dev *pdev);
 bool xe_configfs_get_survivability_mode(struct pci_dev *pdev);
 u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev);
 bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev);
+u32 xe_configfs_get_ctx_restore_post_bb(struct pci_dev *pdev, enum xe_engine_class,
+					const u32 **cs);
 #else
 static inline int xe_configfs_init(void) { return 0; }
 static inline void xe_configfs_exit(void) { }
 static inline void xe_configfs_check_device(struct pci_dev *pdev) { }
 static inline bool xe_configfs_get_survivability_mode(struct pci_dev *pdev) { return false; }
 static inline u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev) { return U64_MAX; }
 static inline bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev) { return false; }
+static inline u32 xe_configfs_get_ctx_restore_post_bb(struct pci_dev *pdev, enum xe_engine_class,
+						      const u32 **cs) { return 0; }
 #endif
 
 #endif

drivers/gpu/drm/xe/xe_lrc.c

@@ -8,6 +8,7 @@
 #include <generated/xe_wa_oob.h>
 
 #include <linux/ascii85.h>
+#include <linux/panic.h>
 
 #include "instructions/xe_mi_commands.h"
 #include "instructions/xe_gfxpipe_commands.h"
@@ -16,6 +17,7 @@
 #include "regs/xe_lrc_layout.h"
 #include "xe_bb.h"
 #include "xe_bo.h"
+#include "xe_configfs.h"
 #include "xe_device.h"
 #include "xe_drm_client.h"
 #include "xe_exec_queue_types.h"
@@ -1102,6 +1104,35 @@ static ssize_t setup_timestamp_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	return cmd - batch;
 }
 
+static ssize_t setup_configfs_post_ctx_restore_bb(struct xe_lrc *lrc,
+						  struct xe_hw_engine *hwe,
+						  u32 *batch, size_t max_len)
+{
+	struct xe_device *xe = gt_to_xe(lrc->gt);
+	const u32 *user_batch;
+	u32 *cmd = batch;
+	u32 count;
+
+	count = xe_configfs_get_ctx_restore_post_bb(to_pci_dev(xe->drm.dev),
+						    hwe->class, &user_batch);
+	if (!count)
+		return 0;
+
+	if (count > max_len)
+		return -ENOSPC;
+
+	/*
+	 * This should be used only for tests and validation. Taint the kernel
+	 * as anything could be submitted directly in context switches
+	 */
+	add_taint(TAINT_TEST, LOCKDEP_STILL_OK);
+
+	memcpy(cmd, user_batch, count * sizeof(u32));
+	cmd += count;
+
+	return cmd - batch;
+}
+
 static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc,
 					       struct xe_hw_engine *hwe,
 					       u32 *batch, size_t max_len)
@@ -1203,6 +1234,7 @@ int xe_lrc_setup_wa_bb_with_scratch(struct xe_lrc *lrc, struct xe_hw_engine *hwe
 		{ .setup = setup_timestamp_wa },
 		{ .setup = setup_invalidate_state_cache_wa },
 		{ .setup = setup_utilization_wa },
+		{ .setup = setup_configfs_post_ctx_restore_bb },
 	};
 	struct bo_setup_state state = {
 		.lrc = lrc,